SOTAVerified

Adversarial Purification

A class of adversarial defense methods that remove adversarial perturbations using a generative model.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 65 papers

TitleStatusHype
Gradient-Free Adversarial Purification with Diffusion Models—0
Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification—0
Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds—0
Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial AttacksCode0
Random Sampling for Diffusion-based Adversarial PurificationCode0
Adversarial Attacks and Robust Defenses in Speaker Embedding based Zero-Shot Text-to-Speech System—0
Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training—0
Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion ModelsCode0
High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image SynthesisCode0
LoRID: Low-Rank Iterative Diffusion for Adversarial Purification—0
Show:102550
← PrevPage 2 of 7Next →

No leaderboard results yet.